Dynamic CNNs Using Uncertainty To Overcome Domain Generalization for Surgical Instrument Localization

Markus Philipp, Anna Alperovich, Marielena Gutt-Will, Andrea Mathis, Stefan Saur, Andreas Raabe, Franziska Mathis-Ullrich; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 3612-3621

Abstract


Due to the limited amount of available annotated data in the medical field, domain generalization for applications in computer-assisted surgery is essential. Our work addresses this problem for the task of surgical instrument tip localization in neurosurgery, which is a classical step towards computer-assisted surgery. We propose an uncertainty-based CNN approach that dynamically selects the most relevant data source by incorporating its own uncertainty into the inference. In addition, the estimated uncertainty can visualize and easily explain the network's decision. Quantitative and qualitative evaluations show that our method outperforms state of the art approaches for large domain shifts and results are on-par for in-domain applications. Further increasing domain shifts by testing on different surgical disciplines, eye and laparoscopic surgeries, proves the generalization capabilities of the proposed method.

Related Material


[pdf] [supp]
[bibtex]
@InProceedings{Philipp_2022_WACV, author = {Philipp, Markus and Alperovich, Anna and Gutt-Will, Marielena and Mathis, Andrea and Saur, Stefan and Raabe, Andreas and Mathis-Ullrich, Franziska}, title = {Dynamic CNNs Using Uncertainty To Overcome Domain Generalization for Surgical Instrument Localization}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {3612-3621} }